add criteria-first discovery search provider

apps/api/tests/test_search_provider.py

@@ -0,0 +1,44 @@
+import os
+import unittest
+from unittest.mock import patch
+
+from app.search_provider import ProviderConfigError, provider_status, search
+
+
+class SearchProviderTests(unittest.TestCase):
+    def tearDown(self):
+        for key in ("SEARCH_PROVIDER_URL", "SEARCH_PROVIDER_ALLOWED_HOSTS", "SEARCH_PROVIDER_API_KEY"):
+            os.environ.pop(key, None)
+
+    def test_not_configured_is_fail_closed(self):
+        self.assertEqual(provider_status()["status"], "not_configured")
+        with self.assertRaisesRegex(ProviderConfigError, "not_configured"):
+            search({"keywords": ["solar"]}, 5)
+
+    def test_unsafe_provider_is_rejected(self):
+        os.environ["SEARCH_PROVIDER_URL"] = "http://search.example.test/query"
+        os.environ["SEARCH_PROVIDER_ALLOWED_HOSTS"] = "search.example.test"
+        self.assertEqual(provider_status()["status"], "unsafe_configured")
+        with self.assertRaisesRegex(ProviderConfigError, "unsafe_provider"):
+            search({}, 5)
+
+    def test_successful_mocked_search_returns_bounded_https_urls(self):
+        os.environ["SEARCH_PROVIDER_URL"] = "https://search.example.test/query"
+        os.environ["SEARCH_PROVIDER_ALLOWED_HOSTS"] = "search.example.test"
+        response = type("Response", (), {"__enter__": lambda self: self, "__exit__": lambda self, *args: None, "read": lambda self, *_: b'{"results":[{"url":"https://acme.test"},{"url":"http://bad.test"},{"url":"https://acme.test"}]}'})()
+        with patch("app.search_provider.urlopen", return_value=response), patch("app.search_provider.validate_url", side_effect=lambda url, **_: url):
+            self.assertEqual(search({"keywords": ["solar"]}, 5), ["https://acme.test"])
+
+    def test_limit_is_bounded_and_sent_to_provider(self):
+        os.environ["SEARCH_PROVIDER_URL"] = "https://search.example.test/query"
+        os.environ["SEARCH_PROVIDER_ALLOWED_HOSTS"] = "search.example.test"
+        response = type("Response", (), {"__enter__": lambda self: self, "__exit__": lambda self, *args: None, "read": lambda self, *_: b'{"results":[]}'})()
+        with patch("app.search_provider.urlopen", return_value=response) as opened:
+            self.assertEqual(search({}, 500), [])
+            self.assertEqual(opened.call_args.kwargs["timeout"], 8)
+            request = opened.call_args.args[0]
+            self.assertIn(b'"limit":50', request.data)
+
+
+if __name__ == "__main__":
+    unittest.main()